用大模型精准生成与查询相关的事件时间线，提升工业搜索体验。
Large Language Model-Powered Query-Driven Event Timeline Summarization in Industrial Search
- 基于多任务微调和强化学习，构建轻量高效的时间线摘要系统。
- 7B模型达76.2% F1，仅用1%参数超越671B大模型的零样本表现。
- 适合需要实时事件理解与低延迟响应的搜索引擎场景。
理解事件随时间演变对处理热点新闻查询的搜索引擎至关重要。我们提出QDET（查询驱动事件时间线摘要），部署于百度搜索的生产系统，旨在为特定查询事件构建聚焦的时间线。不同于传统以主题为中心、追求全面覆盖的方法，QDET从每日数百万文档中筛选出的噪声候选集中，识别并组织与查询紧密相关的子事件。系统包含两项关键创新：(1) 通过三个辅助任务——时间排序、因果判断和时间线补全——进行多任务监督微调，使小型模型在专业领域性能媲美大型通用模型；(2) 基于强化学习的事件摘要压缩机制，在严格长度约束下保持语义质量，实现88.2%的长度合规率，并在约束满足度上比671B规模模型高出7.7分。经微调的7B参数模型在时间线摘要任务上取得76.2% F1分数，略超DeepSeek-R1-671B的零样本表现（76.1%），仅使用其1%参数，证明领域优化可实现高质量、低计算成本的生产级模型。百度搜索在线A/B测试验证其有效性：点击率提升5.5%，停留时长增加4.6%，探索深度提高4.4%。此外，时间线理解能力可迁移至热度预测任务，证实知识转移的有效性。
原文摘要 · Abstract (English)
Understanding how events evolve over time is essential for search engines handling queries about trending news. We present QDET (Query-Driven Event Timeline Summarization), a production system deployed on Baidu Search that constructs focused event timelines to explain specific query events. Unlike traditional topic-centric approaches that aim for comprehensive coverage, QDET identifies and organizes sub-events closely relevant to the query from noisy candidate sets formed by millions of documents retrieved daily. QDET incorporates two key innovations: (1) multi-task supervised fine-tuning with three auxiliary tasks-temporal ordering, causal judgment, and timeline completion-that enable compact models to match the performance of much larger general-purpose models in specialized domains; (2) reinforcement learning-based event concise summarization that enforces strict length constraints while maintaining semantic quality, achieving 88.2% length compliance and outperforming 671B-scale models by 7.7 points in constraint satisfaction. Our fine-tuned 7B parameter model achieves 76.2% F1 score on timeline summarization, slightly surpassing the zero-shot performance of DeepSeek-R1-671B (76.1% F1) while using only 1% of its parameters-demonstrating that domain-specific optimization enables production-ready models with comparable quality at drastically reduced computational costs. Online A/B tests on Baidu Search validate real-world effectiveness, showing 5.5% CTR improvement, 4.6% longer dwell time, and 4.4% deeper exploration compared to single-task baselines. We further demonstrate that timeline understanding transfers to heat prediction, confirming effective knowledge transfer to downstream tasks.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。